model compression

Training Debiased Subnetworks With Contrastive Weight Pruning CVPR 2023 Train-Once-for-All Personalization CVPR 2023 Tunable Soft Prompts are Messengers in Federated Learning EMNLP 2023 TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning ICLR 2023 Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression Interspeech 2023 Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases ICML 2023 Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers NeurIPS 2023 Understanding the Effect of Model Compression on Social Bias in Large Language Models EMNLP 2023 Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study WACV 2023 Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning ICCV 2023 UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors ICCV 2023 UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers ICML 2023 UPSCALE: Unconstrained Channel Pruning ICML 2023 Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules EMNLP 2023 ViM: Vision Middleware for Unified Downstream Transferring ICCV 2023 What Knowledge Gets Distilled in Knowledge Distillation? NeurIPS 2023 WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting NeurIPS 2023 XiNet: Efficient Neural Networks for tinyML ICCV 2023 YANMTT: Yet Another Neural Machine Translation Toolkit ACL 2023 You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model CVPR 2023 You Only Condense Once: Two Rules for Pruning Condensed Datasets NeurIPS 2023 ZipLM: Inference-Aware Structured Pruning of Language Models NeurIPS 2023 Accelerated Federated Learning with Decoupled Adaptive Optimization ICML 2022 Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization Interspeech 2022 Accelerating Inference for Pretrained Language Models by Unified Multi-Perspective Early Exiting COLING 2022